Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    drawing dots

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Personensuche
    1.29
     StatusCode
    1.26
    ⁃
    1.15
     authorizes
    1.15
    驃
    1.14
     echter
    1.14
    簫
    1.12
     startDate
    1.11
     PPE
    1.08
     spicy
    1.08
    POSITIVE LOGITS
    ainer
    1.05
     grandchildren
    1.05
    ito
    1.03
    adas
    1.02
    $("
    0.99
    units
    0.99
    ages
    0.97
    Children
    0.97
    ising
    0.96
    ArrayIndex
    0.94
    Act Density 0.001%

    No Known Activations